[Makedumpfile PATCH v2 0/2] Fix refiltering when kaslr enabled

[Pratyush Anand]

Hi All,

We came across another failure in makedumpfile when kaslr is enabled. This
failure occurs when we try re-filtering. We try to erase some symbol from a
dumpfile which was copied/compressed from /proc/vmcore using makedumpfile.

We have very limited symbol information in vmcoreinfo. So symbols to be
erased may not be available in vmcoreinfo and we look for it in vmlinux.
However, symbol address from vmlinux is a static address which differs
from run time address with KASLR_OFFSET. Therefore, reading any "virtual
address of vmlinux" from vmcore is not possible.

These patches finds runtime KASLR offset and then calculates run time
address of symbols read from vmlinux.

Since, I am not an expert of x86, and these patches touch x86 part of
makedumpfile, therefore I have CCed x86 experts. Please, provide your
review comment and let me know if you think there could have been a better
way to resolve this issue.

thanks

~Pratyush

v1->v2:
- reading KERNELOFFSET from vmcoreinfo now instead of calculating it from
_stext

Pratyush Anand (2):
makedumpfile: add runtime kaslr offset if it exists
x86_64: calculate page_offset in case of re-filtering

arch/x86_64.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
erase_info.c | 1 +
makedumpfile.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
makedumpfile.h | 16 ++++++++++++++++
4 files changed, 124 insertions(+), 2 deletions(-)

[Pratyush Anand]

If we have to erase a symbol from vmcore whose address is not present in
vmcoreinfo, then we need to pass vmlinux as well to get the symbol
address.
When kaslr is enabled, virtual address of all the kernel symbols are
randomized with an offset. vmlinux always has a static address, but all
the arch specific calculation are based on run time kernel address. So
we need to find a way to translate symbol address from vmlinux to kernel
run time address.

without this patch:
# cat > scrub.conf << EOF
[vmlinux]
erase jiffies
erase init_task.utime
for tsk in init_task.tasks.next within task_struct:tasks
erase tsk.utime
endfor
EOF

# makedumpfile --split -d 5 -x vmlinux --config scrub.conf vmcore dumpfile_{1,2,3}

readpage_kdump_compressed: pfn(f97ea) is excluded from vmcore.
readmem: type_addr: 1, addr:f97eaff8, size:8
vtop4_x86_64: Can't get pml4 (page_dir:f97eaff8).
readmem: Can't convert a virtual address(ffffffff819f1284) to physical address.
readmem: type_addr: 0, addr:ffffffff819f1284, size:390
check_release: Can't get the address of system_utsname.

After this patch check_release() is ok, and also we are able to erase
symbol from vmcore.

Signed-off-by: Pratyush Anand <***@redhat.com>
---
arch/x86_64.c | 36 ++++++++++++++++++++++++++++++++++++
erase_info.c | 1 +
makedumpfile.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
makedumpfile.h | 16 ++++++++++++++++
4 files changed, 104 insertions(+)

diff --git a/arch/x86_64.c b/arch/x86_64.c
index e978a36f8878..3116811d7563 100644
--- a/arch/x86_64.c
+++ b/arch/x86_64.c
@@ -33,6 +33,42 @@ get_xen_p2m_mfn(void)
return NOT_FOUND_LONG_VALUE;
}

+unsigned long
+get_kaslr_offset_x86_64(unsigned long vaddr)
+{
+ unsigned int i;
+ char buf[BUFSIZE_FGETS], *endp;
+
+ if (!info->kaslr_offset && info->file_vmcoreinfo) {
+ if (fseek(info->file_vmcoreinfo, 0, SEEK_SET) < 0) {
+ ERRMSG("Can't seek the vmcoreinfo file(%s). %s\n",
+ info->name_vmcoreinfo, strerror(errno));
+ return FALSE;
+ }
+
+ while (fgets(buf, BUFSIZE_FGETS, info->file_vmcoreinfo)) {
+ i = strlen(buf);
+ if (!i)
+ break;
+ if (buf[i - 1] == '\n')
+ buf[i - 1] = '\0';
+ if (strncmp(buf, STR_KERNELOFFSET,
+ strlen(STR_KERNELOFFSET)) == 0)
+ info->kaslr_offset =
+ strtol(buf+strlen(STR_KERNELOFFSET),&endp,16);
+ }
+ }
+ if (vaddr >= __START_KERNEL_map &&
+ vaddr < __START_KERNEL_map + info->kaslr_offset)
+ return info->kaslr_offset;
+ else
+ /*
+ * TODO: we need to check if it is vmalloc/vmmemmap/module
+ * address, we will have different offset
+ */
+ return 0;
+}
+
static int
get_page_offset_x86_64(void)
{
diff --git a/erase_info.c b/erase_info.c
index f2ba9149e93e..60abfa1a1adf 100644
--- a/erase_info.c
+++ b/erase_info.c
@@ -1088,6 +1088,7 @@ resolve_config_entry(struct config_entry *ce, unsigned long long base_vaddr,
ce->line, ce->name);
return FALSE;
}
+ ce->sym_addr += get_kaslr_offset(ce->sym_addr);
ce->type_name = get_symbol_type_name(ce->name,
DWARF_INFO_GET_SYMBOL_TYPE,
&ce->size, &ce->type_flag);
diff --git a/makedumpfile.c b/makedumpfile.c
index 301772a8820c..57235690569e 100644
--- a/makedumpfile.c
+++ b/makedumpfile.c
@@ -2099,6 +2099,13 @@ void
write_vmcoreinfo_data(void)
{
/*
+ * write 1st kernel's KERNELOFFSET
+ */
+ if (info->kaslr_offset)
+ fprintf(info->file_vmcoreinfo, "%s%lx\n", STR_KERNELOFFSET,
+ info->kaslr_offset);
+
+ /*
* write 1st kernel's OSRELEASE
*/
fprintf(info->file_vmcoreinfo, "%s%s\n", STR_OSRELEASE,
@@ -3782,6 +3789,46 @@ free_for_parallel()
}

int
+find_kaslr_offsets()
+{
+ off_t offset;
+ unsigned long size;
+ int ret = FALSE;
+
+ get_vmcoreinfo(&offset, &size);
+
+ if (!(info->name_vmcoreinfo = strdup(FILENAME_VMCOREINFO))) {
+ MSG("Can't duplicate strings(%s).\n", FILENAME_VMCOREINFO);
+ return FALSE;
+ }
+ if (!copy_vmcoreinfo(offset, size))
+ goto out;
+
+ if (!open_vmcoreinfo("r"))
+ goto out;
+
+ unlink(info->name_vmcoreinfo);
+
+ /*
+ * This arch specific function should update info->kaslr_offset. If
+ * kaslr is not enabled then offset will be set to 0. arch specific
+ * function might need to read from vmcoreinfo, therefore we have
+ * called this function between open_vmcoreinfo() and
+ * close_vmcoreinfo()
+ */
+ get_kaslr_offset(SYMBOL(_stext));
+
+ close_vmcoreinfo();
+
+ ret = TRUE;
+out:
+ free(info->name_vmcoreinfo);
+ info->name_vmcoreinfo = NULL;
+
+ return ret;
+}
+
+int
initial(void)
{
off_t offset;
@@ -3833,6 +3880,9 @@ initial(void)
set_dwarf_debuginfo("vmlinux", NULL,
info->name_vmlinux, info->fd_vmlinux);

+ if (has_vmcoreinfo() && !find_kaslr_offsets())
+ return FALSE;
+
if (!get_symbol_info())
return FALSE;

@@ -11031,6 +11081,7 @@ main(int argc, char *argv[])
info->fd_memory = -1;
info->fd_dumpfile = -1;
info->fd_bitmap = -1;
+ info->kaslr_offset = 0;
initialize_tables();

/*
diff --git a/makedumpfile.h b/makedumpfile.h
index e32e567018f6..9f16becadd55 100644
--- a/makedumpfile.h
+++ b/makedumpfile.h
@@ -253,10 +253,14 @@ static inline int string_exists(char *s) { return (s ? TRUE : FALSE); }
#define SYMBOL_INIT(symbol, str_symbol) \
do { \
SYMBOL(symbol) = get_symbol_addr(str_symbol); \
+ if (SYMBOL(symbol) != NOT_FOUND_SYMBOL) \
+ SYMBOL(symbol) += info->kaslr_offset; \
} while (0)
#define SYMBOL_INIT_NEXT(symbol, str_symbol) \
do { \
SYMBOL(symbol) = get_next_symbol_addr(str_symbol); \
+ if (SYMBOL(symbol) != NOT_FOUND_SYMBOL) \
+ SYMBOL(symbol) += info->kaslr_offset; \
} while (0)
#define WRITE_SYMBOL(str_symbol, symbol) \
do { \
@@ -495,6 +499,7 @@ do { \
#define STR_CONFIG_X86_PAE "CONFIG_X86_PAE=y"
#define STR_CONFIG_PGTABLE_4 "CONFIG_PGTABLE_4=y"
#define STR_CONFIG_PGTABLE_3 "CONFIG_PGTABLE_3=y"
+#define STR_KERNELOFFSET "KERNELOFFSET="

/*
* common value
@@ -838,6 +843,7 @@ int get_xen_info_arm64(void);
#define get_phys_base() get_phys_base_arm64()
#define get_machdep_info() get_machdep_info_arm64()
#define get_versiondep_info() get_versiondep_info_arm64()
+#define get_kaslr_offset(X) FALSE
#define get_xen_basic_info_arch(X) get_xen_basic_info_arm64(X)
#define get_xen_info_arch(X) get_xen_info_arm64(X)
#define is_phys_addr(X) stub_true_ul(X)
@@ -851,6 +857,7 @@ unsigned long long vaddr_to_paddr_arm(unsigned long vaddr);
#define get_phys_base() get_phys_base_arm()
#define get_machdep_info() get_machdep_info_arm()
#define get_versiondep_info() stub_true()
+#define get_kaslr_offset(X) FALSE
#define vaddr_to_paddr(X) vaddr_to_paddr_arm(X)
#define is_phys_addr(X) stub_true_ul(X)
#endif /* arm */
@@ -863,11 +870,13 @@ unsigned long long vaddr_to_paddr_x86(unsigned long vaddr);
#define get_phys_base() stub_true()
#define get_machdep_info() get_machdep_info_x86()
#define get_versiondep_info() get_versiondep_info_x86()
+#define get_kaslr_offset(X) FALSE
#define vaddr_to_paddr(X) vaddr_to_paddr_x86(X)
#define is_phys_addr(X) stub_true_ul(X)
#endif /* x86 */

#ifdef __x86_64__
+unsigned long get_kaslr_offset_x86_64(unsigned long vaddr);
int get_phys_base_x86_64(void);
int get_machdep_info_x86_64(void);
int get_versiondep_info_x86_64(void);
@@ -876,6 +885,7 @@ unsigned long long vtop4_x86_64(unsigned long vaddr);
#define get_phys_base() get_phys_base_x86_64()
#define get_machdep_info() get_machdep_info_x86_64()
#define get_versiondep_info() get_versiondep_info_x86_64()
+#define get_kaslr_offset(X) get_kaslr_offset_x86_64(X)
#define vaddr_to_paddr(X) vtop4_x86_64(X)
#define is_phys_addr(X) stub_true_ul(X)
#endif /* x86_64 */
@@ -888,6 +898,7 @@ unsigned long long vaddr_to_paddr_ppc64(unsigned long vaddr);
#define get_phys_base() stub_true()
#define get_machdep_info() get_machdep_info_ppc64()
#define get_versiondep_info() get_versiondep_info_ppc64()
+#define get_kaslr_offset(X) FALSE
#define vaddr_to_paddr(X) vaddr_to_paddr_ppc64(X)
#define is_phys_addr(X) stub_true_ul(X)
#endif /* powerpc64 */
@@ -899,6 +910,7 @@ unsigned long long vaddr_to_paddr_ppc(unsigned long vaddr);
#define get_phys_base() stub_true()
#define get_machdep_info() get_machdep_info_ppc()
#define get_versiondep_info() stub_true()
+#define get_kaslr_offset(X) FALSE
#define vaddr_to_paddr(X) vaddr_to_paddr_ppc(X)
#define is_phys_addr(X) stub_true_ul(X)
#endif /* powerpc32 */
@@ -911,6 +923,7 @@ int is_iomem_phys_addr_s390x(unsigned long addr);
#define get_phys_base() stub_true()
#define get_machdep_info() get_machdep_info_s390x()
#define get_versiondep_info() stub_true()
+#define get_kaslr_offset(X) FALSE
#define vaddr_to_paddr(X) vaddr_to_paddr_s390x(X)
#define is_phys_addr(X) is_iomem_phys_addr_s390x(X)
#endif /* s390x */
@@ -923,6 +936,7 @@ unsigned long long vaddr_to_paddr_ia64(unsigned long vaddr);
#define get_machdep_info() get_machdep_info_ia64()
#define get_phys_base() get_phys_base_ia64()
#define get_versiondep_info() stub_true()
+#define get_kaslr_offset(X) FALSE
#define vaddr_to_paddr(X) vaddr_to_paddr_ia64(X)
#define VADDR_REGION(X) (((unsigned long)(X)) >> REGION_SHIFT)
#define is_phys_addr(X) stub_true_ul(X)
@@ -1152,6 +1166,7 @@ struct DumpInfo {
int vmemmap_psize;
int vmemmap_cnt;
struct ppc64_vmemmap *vmemmap_list;
+ unsigned long kaslr_offset;

/*
* page table info for ppc64
@@ -1803,6 +1818,7 @@ struct memory_range {
struct memory_range crash_reserved_mem[CRASH_RESERVED_MEM_NR];
int crash_reserved_mem_nr;

+unsigned long read_vmcoreinfo_symbol(char *str_symbol);
int readmem(int type_addr, unsigned long long addr, void *bufptr, size_t size);
int get_str_osrelease_from_vmlinux(void);
int read_vmcoreinfo_xen(void);

[Pratyush Anand]

we do not call get_elf_info() in case of refiltering. Therefore, we will
not have any pt_load in that case, and so we get:

get_page_offset_x86_64: Can't get any pt_load to calculate page offset.

However, we will have vmcoreinfo and vmlinux information in case of
re-filtering. So, we are able to find kaslr offset and we can get
page_offset_base address. Thus we can read the page offset as well.
However, if kaslr is not enabled then use old method to find fixed page
offset.

Signed-off-by: Pratyush Anand <***@redhat.com>
---
arch/x86_64.c | 22 ++++++++++++++++++++--
1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/x86_64.c b/arch/x86_64.c
index 3116811d7563..8a50998aa470 100644
--- a/arch/x86_64.c
+++ b/arch/x86_64.c
@@ -75,6 +75,7 @@ get_page_offset_x86_64(void)
int i;
unsigned long long phys_start;
unsigned long long virt_start;
+ unsigned long page_offset_base;

for (i = 0; get_pt_load(i, &phys_start, NULL, &virt_start, NULL); i++) {
if (virt_start < __START_KERNEL_map
@@ -84,8 +85,25 @@ get_page_offset_x86_64(void)
}
}

- ERRMSG("Can't get any pt_load to calculate page offset.\n");
- return FALSE;
+ if (!info->flag_refiltering) {
+ ERRMSG("Can't get any pt_load to calculate page offset.\n");
+ return FALSE;
+ }
+ if (info->kaslr_offset) {
+ page_offset_base = get_symbol_addr("page_offset_base");
+ page_offset_base += info->kaslr_offset;
+ if (!readmem(VADDR, page_offset_base, &info->page_offset,
+ sizeof(info->page_offset))) {
+ ERRMSG("Can't read page_offset_base.\n");
+ return FALSE;
+ }
+ } else if (info->kernel_version < KERNEL_VERSION(2, 6, 27)) {
+ info->page_offset = __PAGE_OFFSET_ORIG;
+ } else {
+ info->page_offset = __PAGE_OFFSET_2_6_27;
+ }
+
+ return TRUE;
}

int